Downscaling smap soil moisture retrievals over an agricultural region in central mexico using machine learning

Juan Carlos Hernández-Sánchez; Alejandro Monsiváis-Huertero; Jasmeet Judge; José Carlos Jiménez-Escalona

doi:10.1109/IGARSS.2019.8900285

Downscaling smap soil moisture retrievals over an agricultural region in central mexico using machine learning

Juan Carlos Hernández-Sánchez, Alejandro Monsiváis-Huertero, Jasmeet Judge, José Carlos Jiménez-Escalona

Escuela Superior de Ingeniería Mecánica y Eléctrica (ESIME), Unidad Ticomán

Research output: Contribution to conference › Paper › peer-review

3 Scopus citations

Abstract

Soil moisture (SM) is an important land surface variable for understanding the water cycle, ecosystem productivity, and linkages between water-carbon cycles. For agricultural applications, SM information is needed at higher resolutions (about 1km). In this study, coarse-scale remotely sensed SM at 36 km from NASA-SMAP was disaggregated to 1 km using high resolution auxiliary information such as land cover, precipitation, land surface temperature, NDVI for a growing season of corn in 2018 in Central Mexico (CM). The main objective is to evaluate a machine-learning based downscaling algorithm over an agricultural area with very limited in-situ observations of SM obtained during THExMEX-18. We found that overall, the downscaled moisture captured the dynamics during the growing season observed by the in-situ measurements.

Original language	English
Pages	7049-7052
Number of pages	4
DOIs	https://doi.org/10.1109/IGARSS.2019.8900285
State	Published - 2019
Event	39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Yokohama, Japan Duration: 28 Jul 2019 → 2 Aug 2019

Conference

Conference	39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019
Country/Territory	Japan
City	Yokohama
Period	28/07/19 → 2/08/19

Keywords

Agriculture
Central Mexico
Machine learning
Passive microwave observations
SMAP downscaling

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/IGARSS.2019.8900285

Cite this

Hernández-Sánchez, J. C., Monsiváis-Huertero, A., Judge, J., & Jiménez-Escalona, J. C. (2019). Downscaling smap soil moisture retrievals over an agricultural region in central mexico using machine learning. 7049-7052. Paper presented at 39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019, Yokohama, Japan. https://doi.org/10.1109/IGARSS.2019.8900285

@conference{ca1b7052faac4705807f0d95cca34e47,

title = "Downscaling smap soil moisture retrievals over an agricultural region in central mexico using machine learning",

abstract = "Soil moisture (SM) is an important land surface variable for understanding the water cycle, ecosystem productivity, and linkages between water-carbon cycles. For agricultural applications, SM information is needed at higher resolutions (about 1km). In this study, coarse-scale remotely sensed SM at 36 km from NASA-SMAP was disaggregated to 1 km using high resolution auxiliary information such as land cover, precipitation, land surface temperature, NDVI for a growing season of corn in 2018 in Central Mexico (CM). The main objective is to evaluate a machine-learning based downscaling algorithm over an agricultural area with very limited in-situ observations of SM obtained during THExMEX-18. We found that overall, the downscaled moisture captured the dynamics during the growing season observed by the in-situ measurements.",

keywords = "Agriculture, Central Mexico, Machine learning, Passive microwave observations, SMAP downscaling",

author = "Hern{\'a}ndez-S{\'a}nchez, {Juan Carlos} and Alejandro Monsiv{\'a}is-Huertero and Jasmeet Judge and Jim{\'e}nez-Escalona, {Jos{\'e} Carlos}",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 ; Conference date: 28-07-2019 Through 02-08-2019",

year = "2019",

doi = "10.1109/IGARSS.2019.8900285",

language = "Ingl{\'e}s",

pages = "7049--7052",

}

Hernández-Sánchez, JC, Monsiváis-Huertero, A, Judge, J & Jiménez-Escalona, JC 2019, 'Downscaling smap soil moisture retrievals over an agricultural region in central mexico using machine learning', Paper presented at 39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019, Yokohama, Japan, 28/07/19 - 2/08/19 pp. 7049-7052. https://doi.org/10.1109/IGARSS.2019.8900285

Downscaling smap soil moisture retrievals over an agricultural region in central mexico using machine learning. / Hernández-Sánchez, Juan Carlos; Monsiváis-Huertero, Alejandro; Judge, Jasmeet et al.
2019. 7049-7052 Paper presented at 39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019, Yokohama, Japan.

Research output: Contribution to conference › Paper › peer-review

TY - CONF

T1 - Downscaling smap soil moisture retrievals over an agricultural region in central mexico using machine learning

AU - Hernández-Sánchez, Juan Carlos

AU - Monsiváis-Huertero, Alejandro

AU - Judge, Jasmeet

AU - Jiménez-Escalona, José Carlos

PY - 2019

Y1 - 2019

N2 - Soil moisture (SM) is an important land surface variable for understanding the water cycle, ecosystem productivity, and linkages between water-carbon cycles. For agricultural applications, SM information is needed at higher resolutions (about 1km). In this study, coarse-scale remotely sensed SM at 36 km from NASA-SMAP was disaggregated to 1 km using high resolution auxiliary information such as land cover, precipitation, land surface temperature, NDVI for a growing season of corn in 2018 in Central Mexico (CM). The main objective is to evaluate a machine-learning based downscaling algorithm over an agricultural area with very limited in-situ observations of SM obtained during THExMEX-18. We found that overall, the downscaled moisture captured the dynamics during the growing season observed by the in-situ measurements.

AB - Soil moisture (SM) is an important land surface variable for understanding the water cycle, ecosystem productivity, and linkages between water-carbon cycles. For agricultural applications, SM information is needed at higher resolutions (about 1km). In this study, coarse-scale remotely sensed SM at 36 km from NASA-SMAP was disaggregated to 1 km using high resolution auxiliary information such as land cover, precipitation, land surface temperature, NDVI for a growing season of corn in 2018 in Central Mexico (CM). The main objective is to evaluate a machine-learning based downscaling algorithm over an agricultural area with very limited in-situ observations of SM obtained during THExMEX-18. We found that overall, the downscaled moisture captured the dynamics during the growing season observed by the in-situ measurements.

KW - Agriculture

KW - Central Mexico

KW - Machine learning

KW - Passive microwave observations

KW - SMAP downscaling

UR - http://www.scopus.com/inward/record.url?scp=85084531392&partnerID=8YFLogxK

U2 - 10.1109/IGARSS.2019.8900285

DO - 10.1109/IGARSS.2019.8900285

M3 - Artículo

AN - SCOPUS:85084531392

SP - 7049

EP - 7052

T2 - 39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019

Y2 - 28 July 2019 through 2 August 2019

ER -

Downscaling smap soil moisture retrievals over an agricultural region in central mexico using machine learning

Abstract

Conference

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this